REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Concept Representation

2026-09-03

AI Summary

为解决患者个性化医疗概念表示学习问题，提出REFINE方法，通过预算限制下的文本属性图和强化学习策略选择KG上下文，并用LLM进行语义优化。

Abstract

Learning rich medical concept representations is essential for EHR prediction. Text-attributed knowledge graphs (TKGs) provide a natural foundation by organizing heterogeneous medical relations together with textual semantics. However, most existing encoders process concepts uniformly across patients, despite the fact that a code's meaning and predictive value depend on patient-specific clinical context and trajectory. Learning patient-personalized concept representations from TKGs introduces two key challenges: (1) deciding how much KG context to incorporate for each observed code, and (2) aligning semantic information with the patient-specific relational structure. We propose REFINE, a KG-aware budgeted LLM graph refinement framework for patient-personalized medical concept encoding. Starting from a global TKG, REFINE constructs patient-specific temporal graphs. A sequential reinforcement learning policy selects a personalized KG expansion budget for each observed code. The resulting patient graph is processed by a heterogeneous GNN to capture relation-aware structural dependencies, while a frozen LLM uses graph-aware soft prompts to semantically refine concept representations. Experiments on MIMIC-III and MIMIC-IV show that REFINE consistently improves diverse EHR backbones, outperforms strong baselines, and demonstrates robust gains across component ablation, KG selection, and data insufficiency.

Problem

• medical concept representation
• personalized learning
• text-attributed knowledge graphs

Innovation

• budgeted LLM graph refinement
• patient-personalized concept encoding
• sequential reinforcement learning policy
• heterogeneous GNN
• frozen LLM